A multilevel stereo correspondence searching strategy for real-time obstacle detection using linear cameras

This paper presents a method, which performs edge stereo matching at different levels, from significant edges to less significant ones. At each level, the process starts by selecting significant edges with respect to their gradient magnitude. The selected edges are then matched and the obtained pairs are used for matching less significant edges in the next level. The matching procedure is based on a voting scheme by using local and global constraints. The performance of the proposed stereo matching method is evaluated for real-time obstacle detection in front of a vehicle using linear cameras.